Modular Multi-Objective Deep Reinforcement Learning with Decision Values
Journal Title: Annals of Computer Science and Information Systems - Year 2018, Vol 15, Issue
Abstract
In this work we present a method for using Deep Q-Networks (DQNs) in multi-objective environments. Deep Q-Networks provide remarkable performance in single objective problems learning from high-level visual state representations. However, in many scenarios (e.g in robotics, games), the agent needs to pursue multiple objectives simultaneously. We propose an architecture in which separate DQNs are used to control the agent's behaviour with respect to particular objectives. In this architecture we introduce decision values to improve the scalarization of multiple DQNs into a single action. Our architecture enables the decomposition of the agent's behaviour into controllable and replaceable sub-behaviours learned by distinct modules. Moreover, it allows to change the priorities of particular objectives post-learning while preserving the overall performance of the agent. To evaluate our solution we used a game-like simulator in which an agent - provided with high-level visual input - pursues multiple objectives in a 2D world.
Authors and Affiliations
Tomasz Tajmajer
Keywords
Related Articles
- EP ID EP569798
- DOI 10.15439/2018F231
- Views 14
- Downloads 0
The Use of Deep Learning in Speech Enhancement
Deep learning is an emerging area in current scenario. Mostly, Convolutional Neural Network (CNN) and Deep Belief Network (DBN) are used as the model in deep learning. It is termed as Deep Neural Network (DNN). The use o...
ECG signal coding methods in digital systems
Article contains an overview of ECG signal coding methods. The presented methods are used to record and present he raw ECG signal in digital systems. The aim of the presentation is to choose the best technique for use in...
An Intuitionistic Approach for Ranking OTA Websites under Multi Criteria Group Decision Making Framework
The transformations from approaches based on crisp set towards fuzzy set were introduced to include the uncertainty experienced in decision making. But the problem of hesitation about any alternative still prevailed amon...
An Efficient Load Balancing Algorithms in Stream Processing With the Cloud Computing Environment
Fog personal computers is definitely correctly buzzword that is receiving, it provides firms zīmju base might be coming availability specialist knowledge. Impair price serve should you have of superiorities in studying t...
Dataset Enhancement in Hair Follicle Detection: ESENSEI Challenge
In this paper, a solution to ESENSEI data mining challenge concerning the analysis of microscopic hair images is described. The task of the challenge was to detect locations of hair follicles in closeup images of a human...